Cigarette making and plug assembling machine cut stem winnowing automatic control method and system

Abstract

The invention discloses an automatic control method and system for tobacco shred winnowing of a cigarette making and plug assembling machine. The method comprises the steps that stem slivers are removed from tobacco shreds through the tobacco shred winnowing system by means of airflow; the cut stem separating system is used for dispersing and conveying the rejected stem slivers; performing visual identification on the slivers and the tobacco shreds which are conveyed in a dispersed manner through a sliver and tobacco shred visual identification system so as to identify the tobacco shreds and the slivers; the weight of the identified tobacco shreds and the stem slivers is metered by adopting a machine vision target detection algorithm through a stem sliver rejected object weight visual metering module; and the cut stem winnowing system and the cut stem separating system are adjusted according to the metering result of the rejected stem weight visual metering module. According to the cut stem winnowing automatic control method and system for the cigarette making and plug assembling machine, the separation effect of cut stems and cut tobacco can be adjusted in real time, the real-time performance and accuracy of cut tobacco content control in the cut stems are improved, the cigarette puncturing defect is reduced, cut tobacco waste is reduced, manual intervention is reduced, and the automation and informatization level of equipment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco processing, and more specifically, to a method and system for controlling wind selection of cut stems in a tobacco rolling machine. Background Art

[0002] The control of stem shreds sorting in the cigarette making machine is an important part of quality and consumption management. The tobacco stems that cannot be completely removed from the tobacco sheets form a small amount of stem sticks after the shredding and drying stages. The hard and sharp stem sticks seriously affect the sensory and smoking quality of the finished cigarettes. The cigarette making machine uses a wind selection device to separate the tobacco shreds and stem sticks before the cigarettes are formed, which is the last step in the removal of stem sticks. The separated stem sticks are generally mixed with a small amount of tobacco shreds. If the stem stick removal rate is too low, the stem stick content of the cigarette will be too high, which may cause the weight deviation of the cigarette to increase, increase the probability of defects such as cigarette puncture, damage the combustion performance and sensory quality of the cigarette, and affect the stability of product quality; if the stem stick removal rate is too high, the tobacco shreds content in the removed stem sticks will be too high, the tobacco consumption of the cigarette making machine will increase, and the effective utilization rate of tobacco shreds will be reduced.

[0003] At present, after the air selection process, cigarette factories mainly use manual sampling and random inspection to detect the shred content in stems and the amount of stem sticks removed, and adjust them through manual adjustment. Manual sampling is very inconvenient, the management of the amount of stem sticks removed is relatively extensive, and the consumption of shredded tobacco is relatively high.

[0004] Therefore, there is an urgent need for a method and system for controlling the wind selection of stem fibers in a winding and splicing machine. Summary of the invention

[0005] The object of the present invention is to provide a method and system for controlling the wind selection of tobacco shreds in a tobacco roulade to solve the problems in the above-mentioned prior art and to achieve real-time adjustment of the separation effect of tobacco shreds from stems and sticks.

[0006] The present invention provides a method for controlling the wind selection of stem shreds in a roto-joining machine, which comprises the following steps:

[0007] The stem wind selection system uses airflow to remove the stems of tobacco;

[0008] The stem picking rejects are dispersed and transported through the stem separation system;

[0009] The stem and tobacco shreds after dispersed delivery are visually identified by the stem and tobacco shreds visual identification system to identify the tobacco shreds and stems;

[0010] The weight of the identified tobacco and stems is measured by the machine vision target detection algorithm through the stem rejection weight visual measurement module.

[0011] The shredded stem air selection system and the shredded stem separation system are adjusted according to the measurement result of the visual measurement module for the weight of the rejected stems.

[0012] In the above-mentioned method for controlling the selection of shredded stems by wind of a fritter, preferably, the shredded stem separation system is used to disperse and transport the rejected shredded stems, which specifically includes:

[0013] The stalk rejects are dispersed and conveyed by separating and leveling the vibrating screen.

[0014] In the above-mentioned method for controlling the wind selection of cut stems in a roto-rolling machine, preferably, the visual recognition of the cut tobacco and the stems after dispersed transportation by the stem and tobacco visual recognition system is performed to identify the cut tobacco and the stems, which specifically includes:

[0015] Collecting an image of the cut stems to be identified after being dispersed and transported to obtain a cut stem image, wherein the cut stems include stem sticks and / or cut tobacco;

[0016] Extracting stem features based on the stem image;

[0017] The visual recognition result of the cut stem image is obtained by using the cut stem features and a pre-built visual recognition model.

[0018] In the above-mentioned method for controlling the selection of shredded stems by wind in a roulier, preferably, the shredded stems feature includes at least one of a shape feature, a size feature and a color feature,

[0019] The extracting the stem features based on the stem image specifically includes:

[0020] intercepting the outline of each material in the shredded stem image;

[0021] The contour of each material in the shredded stem image is input into a pre-trained shredded stem feature extraction model to obtain shredded stem features, wherein the shredded stem feature extraction model includes an image classification network.

[0022] In the above-mentioned method for controlling the selection of shredded stems by wind of a roulade, preferably, the step of obtaining the visual recognition result of the shredded stem image by using the shredded stem features and a pre-built visual recognition model specifically includes:

[0023] The shredded stem features are input into a pre-built visual recognition model to obtain a visual recognition result of the shredded stem image, wherein the visual recognition model includes a visual recognition model built based on a convolutional neural network.

[0024] In the above-mentioned method for controlling the selection of tobacco shreds by wind of a tobacco maker, preferably, the weight of the identified tobacco shreds and tobacco shreds is measured by a machine vision target detection algorithm through a visual weight measurement module for the rejected tobacco shreds, which specifically includes:

[0025] Collecting an image of the stem-stick rejections to obtain a stem-stick rejection image, wherein the stem-stick rejections include stem sticks and / or shredded tobacco;

[0026] The machine vision target detection algorithm is used to detect the stem stick rejection objects and obtain the position information of a single piece of material in the stem stick rejection objects;

[0027] According to the position information of a single piece of material in the rejected stems, the area of ​​the single piece of material is obtained;

[0028] Using the pre-built area-weight measurement model, the weight of a single piece of material is obtained based on its area information;

[0029] Based on the weight information of a single piece of material, the weight and proportion of stems and shredded tobacco in the stem rejects are calculated.

[0030] In the above-mentioned method for controlling the selection of stem strands by wind of a fritter, preferably, the method of using a machine vision target detection algorithm to detect the target of the stem strand rejection object to obtain the position information of a single material in the stem strand rejection object specifically includes:

[0031] Based on the PP-YOLOE machine vision target detection algorithm, the stem stick rejection object detection is carried out to obtain the position information of a single material in the stem stick rejection object.

[0032] The step of obtaining the area of ​​a single piece of material according to the position information of the single piece of material in the rejected stems specifically includes:

[0033] Extract the outline of each single material according to the position information of each single material;

[0034] According to the contour information of each single material, the area of ​​each single material in the stem rejection is obtained.

[0035] The above-mentioned method for controlling the selection of shredded stems by wind of a roto-joining machine, wherein preferably, the weight of a single strand of material is obtained according to the area information of the single strand of material by using a pre-built area-weight measurement model, specifically comprising:

[0036] Pre-established fitting functions for area and weight;

[0037] Substitute the area of ​​a single material into the fitting function of area and weight to obtain the weight of a single material.

[0038] The step of calculating the weight and ratio of stems and shredded tobacco in the stem rejects according to the weight information of a single material specifically includes:

[0039] The weights of the single pieces of material corresponding to the stem sticks in the stem stick rejection are added together to obtain the weight of the stem sticks in the stem stick rejection;

[0040] The weight of each single piece of tobacco in the stem rejects is added up to obtain the weight of the tobacco in the stem rejects;

[0041] According to the weight of the stems and the weight of the shredded tobacco in the stem rejects, the stem ratio and the shredded tobacco ratio in the stem rejects are obtained.

[0042] The above-mentioned method for controlling the wind selection of shredded stems in a roulier, wherein preferably, the wind selection system for shredded stems and the shredded stem separation system are adjusted according to the measurement result of the visual measurement module for the weight of the rejected stems, specifically comprising:

[0043] According to the measurement result of the visual metering module for the weight of the rejected stems, at least one of the flow rate, wind pressure and air volume in the shredded stem air selection system is adjusted, and / or at least one of the vibrating screen structure, vibration frequency and vibration amplitude in the shredded stem separation system is adjusted.

[0044] The present invention also provides a control system for selecting and controlling the wind of the stalks of a spooling machine using the above method, comprising:

[0045] A stem shred winnowing system, a stem shred separation system, a stem stick tobacco visual identification system, a stem stick rejection weight visual measurement module and a controller, wherein the stem shred winnowing system, the stem shred separation system, the stem stick tobacco visual identification system and the stem stick rejection weight visual measurement module are sequentially arranged and respectively connected to the controller, wherein:

[0046] The cut stem air selection system is used to remove the stems of cut tobacco by using airflow;

[0047] The shredded stem separation system is used to disperse and transport the shredded stems;

[0048] The stem and shredded tobacco visual recognition system is used to visually recognize the stem and shredded tobacco after dispersed transportation, so as to identify the shredded tobacco and stem;

[0049] The stem rejection weight visual measurement module is used to measure the weight of the identified shredded tobacco and stems using a machine vision target detection algorithm;

[0050] The controller is used to adjust the shredded stem air selection system and the shredded stem separation system according to the measurement result of the visual measurement module of the stem rejection weight.

[0051] The present invention provides a method and system for controlling the wind selection of shredded tobacco in a cigarette making machine, which identifies shredded tobacco and stem sticks through visual recognition technology; measures the weight of the identified shredded tobacco and stem sticks through a machine vision target detection algorithm; and adjusts a shredded tobacco wind selection system and a shredded tobacco separation system according to the measurement results of the shredded tobacco and stem sticks, thereby achieving real-time adjustment of the stem stick and tobacco shred separation effect, improving the real-time and accuracy of shred content control in shredded stems, reducing cigarette puncture defects, reducing cigarette weight deviations, reducing shredded tobacco waste, reducing manual intervention, improving equipment automation and informationization levels, achieving optimal balance control of product quality and raw material consumption, providing technical support for cigarette making units in improving quality and reducing consumption, improving lean production, and homogenizing processing capabilities, and providing equipment support for enterprise digital transformation and refined quality management. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention will be further described below with reference to the accompanying drawings, in which:

[0053] Figure 1 A flow chart of an embodiment of a method for controlling the wind selection of stems in a fritter provided by the present invention;

[0054] Figure 2 This is a structural block diagram of an embodiment of the wind-selected automatic control system for the shredded steel pipe roll-up machine provided by the present invention. DETAILED DESCRIPTION

[0055] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. The description of the exemplary embodiments is merely illustrative and is in no way intended to limit the present disclosure and its application or use. The present disclosure can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to make the present disclosure thorough and complete and to fully express the scope of the present disclosure to those skilled in the art. It should be noted that unless otherwise specifically stated, the relative arrangement of the components and steps, the composition of the materials, the numerical expressions and the numerical values ​​set forth in these embodiments should be interpreted as being merely exemplary and not as limiting.

[0056] The words "first", "second" and similar words used in this disclosure do not indicate any order, quantity or importance, but are only used to distinguish different parts. The words "include" or "comprises" and similar words mean that the elements before the word include the elements listed after the word, and do not exclude the possibility of including other elements. "Up", "down" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0057] In the present disclosure, when a specific component is described as being located between a first component and a second component, there may or may not be an intermediate component between the specific component and the first component or the second component. When a specific component is described as being connected to other components, the specific component may be directly connected to the other components without an intermediate component, or may not be directly connected to the other components but have an intermediate component.

[0058] All terms (including technical terms or scientific terms) used in the present disclosure have the same meanings as those understood by ordinary technicians in the field to which the present disclosure belongs, unless otherwise specifically defined. It should also be understood that terms defined in general dictionaries, such as general dictionaries, should be interpreted as having meanings consistent with their meanings in the context of the relevant technology, and should not be interpreted in an idealized or extremely formal sense, unless explicitly defined herein.

[0059] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0060] like Figure 1 As shown, the actual implementation process of the method for controlling the selection of shredded stems by wind in the rouleau provided in this embodiment specifically includes the following steps:

[0061] Step S1, using an airflow to remove tobacco stems through a stem wind selection system.

[0062] Step S2: The stem-cut materials are dispersed and transported through the stem-cut separation system.

[0063] Among them, the stem and stick rejects are dispersed and transported by separating, flattening and vibrating screens.

[0064] Step S3: visually identify the stems and shredded tobacco after dispersed transportation through a stem and shredded tobacco visual recognition system to identify the shredded tobacco and stems.

[0065] In one embodiment of the method for controlling the selection of cut stems by wind in a roto-joining machine of the present invention, the step S3 may specifically include:

[0066] Step S31 , collecting images of the shredded stems to be identified after being dispersed and transported, to obtain shredded stem images.

[0067] Specifically, a high-definition camera is used to capture images of the shredded stems to be identified, and a shredded stem image is obtained. In one embodiment of the present invention, in a specific implementation, the stems rejected by the cigarette making machine can be first passed through a separation, flattening and vibrating screen of a shredded stem separation system and then the image of the stems rejected can be captured by a high-speed line-scan CCD industrial camera. The high-definition camera can ensure that a high-quality shredded stem image is obtained.

[0068] Step S32: extracting the features of the shredded stems based on the shredded stems image.

[0069] The cut stem feature includes at least one of a shape feature, a size feature, and a color feature. In one embodiment of the method for controlling the selection of cut stems by a roll-up machine of the present invention, the step S32 may specifically include:

[0070] Step S321, capturing the outline of each strand of material in the shredded stem image.

[0071] Step S322: input the outline of each piece of material in the shredded stem image into a pre-trained stem feature extraction model to obtain shredded stem features.

[0072] The stem feature extraction model includes an image classification network. By extracting the stem features, it is possible to distinguish the stems from other impurities.

[0073] Furthermore, in some embodiments of the present invention, between step S31 and step S32, step S3 further includes: preprocessing the stem image, and the image quality can be improved by image preprocessing, wherein the preprocessing can be filtering, binarization, etc. The noise in the image can be removed by filtering, and the contrast in the image can be enhanced by binarization. Exemplarily, the stem image can be binarized by threshold segmentation method to facilitate the detection of image edges.

[0074] Step S33: using the shredded stem features and a pre-built visual recognition model to obtain a visual recognition result of the shredded stem image.

[0075] Specifically, the shredded tobacco stem features are input into a pre-constructed visual recognition model to obtain a visual recognition result of the shredded tobacco stem image. The visual recognition model includes a visual recognition model constructed based on a convolutional neural network. By recognizing the shredded tobacco stem image through the visual recognition model, it is possible to accurately distinguish the de-stemmed tobacco from the shredded tobacco, and to improve the accuracy and intelligence of recognition and measurement. In one embodiment of the present invention, the visual recognition model includes a visual recognition model constructed based on a convolutional neural network. It should be noted that the present invention does not specifically limit the type of visual recognition model, and in other embodiments of the present invention, the visual recognition model may also be other types of deep learning models.

[0076] In step S3, based on the shredded stem image, shredded stem features are extracted, and then the shredded stem features and a pre-built visual recognition model are used to obtain a visual recognition result of the shredded stem image, thereby realizing automatic recognition of shredded stems and shredded tobacco, being able to accurately distinguish between de-stemmed tobacco and shredded tobacco, and being able to achieve an accuracy of about 98% in identifying shredded tobacco and shredded stems, thereby improving the accuracy and intelligence of recognition and measurement, and facilitating faster and more accurate weight determination of the identified shredded tobacco and shredded stems, and further calculating the shredded stem rejection rate.

[0077] Step S4: The weight of the identified tobacco shreds and stems is measured by a stem rejection weight visual measurement module using a machine vision target detection algorithm.

[0078] In one embodiment of the method for controlling the selection of shredded stems by wind of a roto-joiner of the present invention, the step S4 may specifically include:

[0079] Step S41, collecting an image of the object to be removed by stems and tags, and obtaining an image of the object to be removed by stems and tags, wherein:

[0080] The shredded stems include stems and / or tobacco shreds. Specifically, an image of the rejected stems is captured by a high-definition camera to obtain an image of the rejected stems. In one embodiment of the present invention, an image of the rejected stems can be captured by a high-speed line scan CCD industrial camera. The high-definition camera can ensure that a high-quality image of the rejected stems is obtained.

[0081] Step S42: Use a machine vision target detection algorithm to perform target detection on the stem stick rejection objects to obtain the position information of a single piece of material in the stem stick rejection objects.

[0082] Specifically, the stalk rejection object detection is performed based on the PP-YOLOE machine vision target detection algorithm to obtain the position information of a single piece of material in the stalk rejection object. PP-YOLOE is one of the latest improved versions of the YOLO series. It is an improved and optimized version based on YOLOv5. PP-YOLOE uses a more powerful backbone network CSPRepResNet, which has better detection performance than YOLOv5. At the same time, PP-YOLOE introduces an adaptive feature fusion module PAN, which can effectively fuse features at different levels, helping to improve the accuracy and robustness of detection. PP-YOLOE also adds a multi-scale prediction mechanism to the network structure, which can simultaneously detect targets of different scales, thereby improving the accuracy and generalization ability of the model.

[0083] Step S43: obtaining the area of ​​a single piece of material according to the position information of the single piece of material in the rejected stems.

[0084] In one embodiment of the method for controlling the selection of shredded stems by wind of a roto-joining machine of the present invention, the step S43 may specifically include:

[0085] Step S431: extract the contour of each single piece of material according to the position information of each single piece of material.

[0086] Specifically, each single piece of material at the corresponding position is preprocessed to extract the outline of the tobacco stem, wherein the preprocessing includes at least one of image filtering, image grayscale processing, binarization processing and threshold segmentation processing.

[0087] Step S432: Obtain the area of ​​each single piece of material in the rejected stems according to the contour information of each single piece of material.

[0088] Specifically, the area of ​​each single material is obtained according to the number of pixels and the pixel accuracy in the contour information corresponding to each single material.

[0089] Step S44: using the pre-built area-weight measurement model, the weight of the single material is obtained according to the area information of the single material.

[0090] In one embodiment of the method for controlling the selection of cut stems by wind of a roto-joining machine of the present invention, the step S44 may specifically include:

[0091] Step S441, pre-establishing a fitting function of area and weight.

[0092] In one embodiment of the present invention, the fitting function of area and weight is a linear function. It should be noted that the present invention does not specifically limit the type of the fitting function of area and weight.

[0093] Step S442: Substitute the area of ​​a single piece of material into the fitting function of area and weight to obtain the weight of the single piece of material.

[0094] Step S45: Calculate the weight and proportion of the stems and shredded tobacco in the stem rejects according to the weight information of the single tobacco.

[0095] In one embodiment of the method for controlling the selection of cut stems by wind of a roto-joining machine of the present invention, the step S45 may specifically include:

[0096] Step S451: sum the weights of the single pieces of material corresponding to the stem sticks in the rejected stem sticks to obtain the weight of the stem sticks in the rejected stem sticks.

[0097] Step S452: sum up the weights of the single pieces of tobacco in the rejected stems to obtain the weight of the tobacco in the rejected stems.

[0098] Step S453: Obtain the stem ratio and the tobacco ratio in the stem rejects according to the weight of the stems and the weight of the tobacco shreds in the stem rejects.

[0099] Specifically, the weight of the stems is divided by the sum of the weights of the stems and the shredded tobacco to obtain the proportion of the stems in the stem rejects, and the weight of the shredded tobacco is divided by the sum of the weights of the stems and the shredded tobacco to obtain the proportion of the shredded tobacco in the stem rejects.

[0100] In step S4, a machine vision target detection algorithm is used to detect the stem stick rejection object, and the position information of a single material in the stem stick rejection object is obtained, and on this basis, the area and weight of the single material are obtained; then the weight and ratio of the stem sticks and tobacco in the stem stick rejection object are calculated; by constructing an online recognition-area calculation-weight online measurement system, and calculating the weight and ratio of the stem sticks and tobacco in real time, the stem stick rejection rate can be calculated quickly and accurately, providing a process value basis for the automatic control of stem and shred separation.

[0101] Step S5: adjusting the shredded stem air selection system and the shredded stem separation system according to the measurement result of the visual measurement module for the weight of the rejected stems.

[0102] Specifically, according to the measurement result of the visual metering module for the weight of the rejected stems, at least one of the flow rate, wind pressure and air volume in the shredded stem air selection system is adjusted, and / or at least one of the vibrating screen structure, vibration frequency and vibration amplitude in the shredded stem separation system is adjusted.

[0103] The embodiment of the present invention provides a control method for the wind selection of shredded tobacco and stem sticks for a cigarette making machine, which identifies shredded tobacco and stem sticks through visual recognition technology; measures the weight of the identified shredded tobacco and stem sticks through a machine vision target detection algorithm; and adjusts the shredded tobacco wind selection system and the shredded tobacco separation system according to the measurement results of the shredded tobacco and stem sticks, thereby achieving real-time adjustment of the shredded tobacco separation effect, improving the real-time and accuracy of the shredded tobacco content control in the shredded stems, reducing cigarette puncture defects, reducing cigarette weight deviations, reducing shredded tobacco waste, reducing manual intervention, and improving the level of equipment automation and informatization, achieving the best balance control of product quality and raw material consumption, providing technical support for cigarette making units in improving quality and reducing consumption, improving lean production, and homogenizing processing capabilities, and providing equipment support for the digital transformation and refined quality management of enterprises.

[0104] Correspondingly, if Figure 2 As shown, the present invention further provides a control system for wind selection of cut stems of a roto-rolling machine, comprising: a wind selection system 101 for cut stems, a cut stem separation system 102, a visual identification system for cut stem tobacco 103, a visual measurement module 104 for weight of cut stem rejection, and a controller 105, wherein the wind selection system 101 for cut stems, the cut stem separation system 102, the visual identification system 103 for cut stem tobacco, and the visual measurement module 104 for weight of cut stem rejection are sequentially arranged and respectively connected to the controller 105, wherein:

[0105] The cut stem air selection system 101 is used to remove the stems from the cut tobacco by using airflow;

[0106] The shredded stem separation system 102 is used to disperse and transport the shredded stems;

[0107] The stem and shredded tobacco visual recognition system 103 is used to visually recognize the stem and shredded tobacco after scattered transportation, so as to identify the shredded tobacco and stem;

[0108] The stem rejection weight visual measurement module 104 is used to measure the weight of the identified tobacco shreds and stems using a machine vision target detection algorithm;

[0109] The controller 105 is used to adjust the shredded stem winnowing system 101 and the shredded stem separation system 102 according to the measurement result of the visual measurement module of the rejected stem weight.

[0110] The controller 105 is a programmable logic controller (PLC). In some embodiments of the present invention, the controller 105 can be placed inside the roll-joiner without changing the overall appearance of the roll-joiner. After the secondary stem shreds are separated, they are visually identified and measured before being sent to the stem recovery channel. The controller adjusts the control parameters related to the secondary separation according to the stem ratio and flow rate to achieve the best balance between product quality and raw material consumption.

[0111] The embodiment of the present invention provides a control system for the wind selection of shredded tobacco and stem sticks for a cigarette maker, which identifies shredded tobacco and stem sticks through visual recognition technology; measures the weight of the identified shredded tobacco and stem sticks through a machine vision target detection algorithm; and adjusts the shredded tobacco wind selection system and the shredded tobacco separation system according to the measurement results of the shredded tobacco and stem sticks, thereby achieving real-time adjustment of the shredded tobacco separation effect, improving the real-time and accuracy of the shredded tobacco content control in the shredded stems, reducing cigarette puncture defects, reducing cigarette weight deviations, reducing tobacco waste, reducing manual intervention, and improving the level of equipment automation and informatization, achieving the best balance between product quality and raw material consumption, providing technical support for cigarette making units in improving quality and reducing consumption, improving lean production, and homogenizing processing capabilities, and providing equipment support for the digital transformation and refined quality management of enterprises.

[0112] So far, various embodiments of the present disclosure have been described in detail. In order to avoid obscuring the concept of the present disclosure, some details known in the art are not described. Based on the above description, those skilled in the art can fully understand how to implement the technical solution disclosed here.

[0113] Although some specific embodiments of the present disclosure have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It should be understood by those skilled in the art that the above embodiments may be modified or some technical features may be replaced by equivalents without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.

Claims

1. A method for controlling the wind selection of stem shreds in a volume-splitting machine, characterized in that: include: The stem wind selection system uses airflow to remove the stems of tobacco; The stem picking rejects are dispersed and transported through the stem separation system; The stem and tobacco shreds after dispersed delivery are visually identified by the stem and tobacco shreds visual identification system to identify the tobacco shreds and stems; The weight of the identified tobacco and stems is measured by the machine vision target detection algorithm through the stem rejection weight visual measurement module. The shredded stem air selection system and the shredded stem separation system are adjusted according to the measurement result of the visual measurement module for the weight of the rejected stems.

2. The method for controlling the selection of stem strands by wind in a roto-joining machine according to claim 1, characterized in that: The method of dispersing and conveying the rejected stems by the stem separation system specifically includes: The stalk rejects are dispersed and conveyed by separating and leveling the vibrating screen.

3. The method for controlling the selection of stem strands by wind in a roto-joining machine according to claim 1, characterized in that: The visual recognition of the stems and tobacco shreds after the scattered delivery by the stem and tobacco shreds visual recognition system to identify the tobacco shreds and stems specifically includes: Collecting an image of the shredded stems to be identified after being dispersed and transported to obtain an image of the shredded stems, wherein the shredded stems include stem sticks and / or shredded tobacco; Extracting stem features based on the stem image; The visual recognition result of the cut stem image is obtained by using the cut stem features and a pre-built visual recognition model.

4. The method for controlling the wind selection of the stem shreds of the roulier according to claim 3, characterized in that: The stem characteristics include at least one of shape characteristics, size characteristics and color characteristics, The extracting the stem features based on the stem image specifically includes: intercepting the outline of each material in the shredded stem image; The contour of each material in the shredded stem image is input into a pre-trained shredded stem feature extraction model to obtain shredded stem features, wherein the shredded stem feature extraction model includes an image classification network.

5. The method for controlling the wind selection of stems in a roto-joining machine according to claim 3, characterized in that: The step of obtaining a visual recognition result of the cut stem image by using the cut stem feature and a pre-built visual recognition model specifically includes: The shredded stem features are input into a pre-built visual recognition model to obtain a visual recognition result of the shredded stem image, wherein the visual recognition model includes a visual recognition model built based on a convolutional neural network.

6. The method for controlling the wind selection of stem shreds in a roto-joining machine according to claim 1, characterized in that: The visual weight measurement module for the rejected stems uses a machine vision target detection algorithm to measure the weight of the identified shredded tobacco and stems, specifically including: Collecting an image of the stem-stick rejections to obtain a stem-stick rejection image, wherein the stem-stick rejections include stem sticks and / or shredded tobacco; The machine vision target detection algorithm is used to detect the stem stick rejection objects and obtain the position information of a single piece of material in the stem stick rejection objects; According to the position information of a single piece of material in the rejected stems, the area of ​​the single piece of material is obtained; Using the pre-built area-weight measurement model, the weight of a single piece of material is obtained based on its area information; Based on the weight information of a single piece of material, the weight and proportion of stems and shredded tobacco in the stem rejects are calculated.

7. The method for controlling the wind selection of stem shreds in a roto-joining machine according to claim 6, characterized in that: The method of using a machine vision target detection algorithm to detect the stem stick rejection target and obtain the position information of a single material in the stem stick rejection specifically includes: Based on the PP-YOLOE machine vision target detection algorithm, the stem stick rejection object detection is carried out to obtain the position information of a single material in the stem stick rejection object. The step of obtaining the area of ​​a single piece of material according to the position information of the single piece of material in the rejected stems specifically includes: Extract the outline of each single material according to the position information of each single material; According to the contour information of each single material, the area of ​​each single material in the stem rejection is obtained.

8. The method for controlling the wind selection of stems in a fritter according to claim 6, characterized in that: The method of using the pre-built area-weight measurement model to obtain the weight of a single piece of material according to the area information of the single piece of material specifically includes: Pre-established fitting functions for area and weight; Substitute the area of ​​a single material into the fitting function of area and weight to obtain the weight of a single material. The step of calculating the weight and ratio of stems and shredded tobacco in the stem rejects according to the weight information of a single material specifically includes: The weights of the single pieces of material corresponding to the stem sticks in the stem stick rejection are added together to obtain the weight of the stem sticks in the stem stick rejection; The weight of each single piece of tobacco in the stem rejects is added up to obtain the weight of the tobacco in the stem rejects; According to the weight of the stems and the weight of the shredded tobacco in the stem rejects, the stem ratio and the shredded tobacco ratio in the stem rejects are obtained.

9. The method for controlling the wind selection of stem shreds in a roto-joining machine according to claim 1, characterized in that: The adjusting of the shredded stem winnowing system and the shredded stem separation system according to the measurement result of the visual measurement module for the weight of the rejected stems specifically includes: According to the measurement result of the visual metering module for the weight of the rejected stems, at least one of the flow rate, wind pressure and air volume in the shredded stem air selection system is adjusted, and / or at least one of the vibrating screen structure, vibration frequency and vibration amplitude in the shredded stem separation system is adjusted.

10. A control system for selecting and controlling the wind of a shredded stem of a volume-splitter using the method of any one of claims 1 to 9, characterized in that: include: A stem shred winnowing system, a stem shred separation system, a stem stick tobacco visual identification system, a stem stick rejection weight visual measurement module and a controller, wherein the stem shred winnowing system, the stem shred separation system, the stem stick tobacco visual identification system and the stem stick rejection weight visual measurement module are sequentially arranged and respectively connected to the controller, wherein: The cut stem air selection system is used to remove the stems of cut tobacco by using airflow; The shredded stem separation system is used to disperse and transport the shredded stems; The stem and shredded tobacco visual recognition system is used to visually recognize the stem and shredded tobacco after dispersed transportation, so as to identify the shredded tobacco and stem; The stem rejection weight visual measurement module is used to measure the weight of the identified shredded tobacco and stems using a machine vision target detection algorithm; The controller is used to adjust the shredded stem air selection system and the shredded stem separation system according to the measurement result of the visual measurement module of the stem rejection weight.

Images